Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.7591. Min Act: -0.1700

Data Index: 6765413 (Open Web Text)

Max Activating Token Index: 517

Text #1

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.3201. Min Act: -0.1700

Data Index: 2109081 (Open Web Text)

Max Activating Token Index: 283

Text #2

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.3040. Min Act: -0.1700

Data Index: 8769776 (Open Web Text)

Max Activating Token Index: 828

Text #3

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.2253. Min Act: -0.1700

Data Index: 7858321 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1881. Min Act: -0.1700

Data Index: 2075977 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.2145. Min Act: -0.1700

Data Index: 7858328 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1999. Min Act: -0.1700

Data Index: 8288935 (Open Web Text)

Max Activating Token Index: 795

Text #7

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.2067. Min Act: -0.1700

Data Index: 1968588 (Open Web Text)

Max Activating Token Index: 246

Text #8

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1787. Min Act: -0.1700

Data Index: 8700022 (Open Web Text)

Max Activating Token Index: 260

Text #9

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1687. Min Act: -0.1700

Data Index: 2729646 (Open Web Text)

Max Activating Token Index: 940

Text #10

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1855. Min Act: -0.1700

Data Index: 2844715 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1566. Min Act: -0.1700

Data Index: 7461925 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1693. Min Act: -0.1700

Data Index: 1014284 (Open Web Text)

Max Activating Token Index: 871

Text #13

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.2034. Min Act: -0.1700

Data Index: 6828 (Open Web Text)

Max Activating Token Index: 749

Text #14

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1742. Min Act: -0.1700

Data Index: 3710102 (Open Web Text)

Max Activating Token Index: 833

Text #15

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1675. Min Act: -0.1700

Data Index: 7997994 (Open Web Text)

Max Activating Token Index: 701

Text #16

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1784. Min Act: -0.1700

Data Index: 7136609 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1456. Min Act: -0.1700

Data Index: 6669213 (Open Web Text)

Max Activating Token Index: 511

Text #18

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1330. Min Act: -0.1700

Data Index: 8801611 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.1402. Min Act: -0.1700

Data Index: 838619 (Open Web Text)

Max Activating Token Index: 200